Textural features reflecting local activity of the hippocampus improve the diagnosis of Alzheimer’s disease and amnestic mild cognitive impairment: A radiomics study based on functional magnetic resonance imaging

Abstract

BackgroundTextural features of the hippocampus in structural magnetic resonance imaging (sMRI) images can serve as potential diagnostic biomarkers for Alzheimer’s disease (AD), while exhibiting a relatively poor discriminant performance in detecting early AD, such as amnestic mild cognitive impairment (aMCI). In contrast to sMRI, functional magnetic resonance imaging (fMRI) can identify brain functional abnormalities in the early stages of cerebral disorders. However, whether the textural features reflecting local functional activity in the hippocampus can improve the diagnostic performance for AD and aMCI remains unclear. In this study, we combined the textural features of the amplitude of low frequency fluctuation (ALFF) in the slow-5 frequency band and structural images in the hippocampus to investigate their diagnostic performance for AD and aMCI using multimodal radiomics technique.MethodsTotally, 84 AD, 50 aMCI, and 44 normal controls (NCs) were included in the current study. After feature extraction and feature selection, the radiomics models incorporating sMRI images, ALFF values and their combinations in the bilateral hippocampus were established for the diagnosis of AD and aMCI. The effectiveness of these models was evaluated by receiver operating characteristic (ROC) analysis. The radiomics models were further validated using the external data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database.ResultsThe results of ROC analysis showed that the radiomics models based on structural images in the hippocampus had a better diagnostic performance for AD compared with the models using ALFF, while the ALFF-based model exhibited better discriminant performance for aMCI than the models with structural images. The radiomics models based on the combinations of structural images and ALFF were found to exhibit the highest accuracy for distinguishing AD from NCs and aMCI from NCs.ConclusionIn this study, we found that the textural features reflecting local functional activity could improve the diagnostic performance of traditional structural models for both AD and aMCI. These findings may deepen our understanding of the pathogenesis of AD, contributing to the early diagnosis of AD.

MRI-based machine learning model: A potential modality for predicting cognitive dysfunction in patients with type 2 diabetes mellitus

“…Sun et al revealed that the reduced functional connectivity of the hippocampus may be closely related to the disruption of white matter integrity ( Sun et al, 2018 ). Wang et al combined the textural features and structural images in the hippocampus to investigate their diagnostic performance for AD and MCI using multimodal radiomics technique, and found that the textural features reflecting local functional activity could improve the diagnostic performance of traditional structural models for both AD and MCI ( Wang et al, 2022 ). This study may lay the groundwork for future research on the brain structural and functional connectivity by radiomics methods since the abnormalities in the brain of patients with T2DM were identified by both the DTI and ML model for the whole cerebrum.…”

A Model for Diagnosing Autism Patients Using Spatial and Statistical Measures Using rs-fMRI and sMRI by Adopting Graphical Neural Networks

“…Two thousand features are selected using Fisher’s score and passed to a stacked autoencoder (4 levels) for dimensionality reduction. Stacked autoencoders produce a latent space that is less sparse, more predictable, continuous [ 23 , 24 ] and yields 150 features. Algorithm 2 specifies the encoding process of the stacked autoencoder.…”

“…The hippocampus is a region of the brain known to be affected by AD and aMCI. The authors aimed to use imaging data to extract textural features that reflect local activity in this region [ 24 ]. Only the hippocampus was considered in their work, and other statistical measures of the brain need to be addressed.…”

A multi-cohort study of the hippocampal radiomics model and its associated biological changes in Alzheimer’s Disease

“…To minimize the bias caused by segmentation uncertainty and increase effectiveness, the automated deep learning-based hippocampal segmentation toolkit Hippodeep was used to segment the bilateral hippocampi [21]. Previous studies have shown that this tool has good reliability and internal consistency for hippocampal segmentation [22,23].…”